An official website of the United States government
Classification tasks on ultra-lightweight devices demand devices that are resource-constrained and deliver swift responses. Binary Vector Symbolic Architecture (VSA) is a promising approach due to its minimal memory requirements and fast execution times compared to traditional machine learning (ML) methods. Nonetheless, binary VSA's practicality is limited by its inferior inference performance and a design that prioritizes algorithmic over hardware optimization. This paper introduces UniVSA, a co-optimized binary VSA framework for both algorithm and hardware. UniVSA not only significantly enhances inference accuracy beyond current state-of-the-art binary VSA models but also reduces memory footprints. It incorporates novel, lightweight modules and design flow tailored for optimal hardware performance. Experimental results show that UniVSA surpasses traditional ML methods in terms of performance on resource-limited devices, achieving smaller memory usage, lower latency, reduced resource demand, and decreased power consumption.
more »
« less
OptimML: Joint Control of Inference Latency and Server Power Consumption for ML Performance Optimization
Power capping is an important technique for high-density servers to safely oversubscribe the power infrastructure in a data center. However, power capping is commonly accomplished by dynamically lowering the server processors’ frequency levels, which can result in degraded application performance. For servers that run important machine learning (ML) applications with Service-Level Objective (SLO) requirements, inference performance such as recognition accuracy must be optimized within a certain latency constraint, which demands high server performance. In order to achieve the best inference accuracy under the desired latency and server power constraints, this paper proposes OptimML, a multi-input-multi-output (MIMO) control framework that jointly controls both inference latency and server power consumption, by flexibly adjusting the machine learning model size (and so its required computing resources) when server frequency needs to be lowered for power capping. Our results on a hardware testbed with widely adopted ML framework (including PyTorch, TensorFlow, and MXNet) show that OptimML achieves higher inference accuracy compared with several well-designed baselines, while respecting both latency and power constraints. Furthermore, an adaptive control scheme with online model switching and estimation is designed to achieve analytic assurance of control accuracy and system stability, even in the face of significant workload/hardware variations.
more »
« less
- Award ID(s):
- 2336886
- PAR ID:
- 10652008
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- ACM Transactions on Autonomous and Adaptive Systems
- ISSN:
- 1556-4665
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Model-serving systems expose machine learning (ML) models to applications programmatically via a high-level API. Cloud plat- forms use these systems to mask the complexities of optimally managing resources and servicing inference requests across multi- ple applications. Model serving at the edge is now also becoming increasingly important to support inference workloads with tight latency requirements. However, edge model serving differs substan- tially from cloud model serving in its latency, energy, and accuracy constraints: these systems must support multiple applications with widely different latency and accuracy requirements on embedded edge accelerators with limited computational and energy resources. To address the problem, this paper presents Dělen,1 a flexible and adaptive model-serving system for multi-tenant edge AI. Dělen exposes a high-level API that enables individual edge applications to specify a bound at runtime on the latency, accuracy, or energy of their inference requests. We efficiently implement Dělen using conditional execution in multi-exit deep neural networks (DNNs), which enables granular control over inference requests, and evalu- ate it on a resource-constrained Jetson Nano edge accelerator. We evaluate Dělen flexibility by implementing state-of-the-art adapta- tion policies using Dělen’s API, and evaluate its adaptability under different workload dynamics and goals when running single and multiple applications.more » « less
-
Low-latency inference for machine learning models is increasingly becoming a necessary requirement, as these models are used in mission-critical applications such as autonomous driving, military defense (e.g., target recognition), and network traffic analysis. A widely studied and used technique to overcome this challenge is to offload some or all parts of the inference tasks onto specialized hardware such as graphic processing units. More recently, offloading machine learning inference onto programmable network devices, such as programmable network interface cards or a programmable switch, is gaining interest from both industry and academia, especially due to the latency reduction and computational benefits of performing inference directly on the data plane where the network packets are processed. Yet, current approaches are relatively limited in scope, and there is a need to develop more general approaches for mapping offloading machine learning models onto programmable network devices. To fulfill such a need, this work introduces a novel framework, called ML-NIC, for deploying trained machine learning models onto programmable network devices' data planes. ML-NIC deploys models directly into the computational cores of the devices to efficiently leverage the inherent parallelism capabilities of network devices, thus providing huge latency and throughput gains. Our experiments show that ML-NIC reduced inference latency by at least 6 × on average and in the 99th percentile and increased throughput by at least 16xwith little to no degradation in model effectiveness compared to the existing CPU solutions. In addition, ML-NIC can provide tighter guaranteed latency bounds in the presence of other network traffic with shorter tail latencies. Furthermore, ML-NIC reduces CPU and host server RAM utilization by 6.65% and 320.80 MB. Finally, ML-NIC can handle machine learning models that are 2.25 × larger than the current state-of-the-art network device offloading approaches.more » « less
-
An emerging use-case of machine learning (ML) is to train a model on a high-performance system and deploy the trained model on energy-constrained embedded systems. Neuromorphic hardware platforms, which operate on principles of the biological brain, can significantly lower the energy overhead of a machine learning inference task, making these platforms an attractive solution for embedded ML systems. We present a design-technology tradeoff analysis to implement such inference tasks on the processing elements (PEs) of a Non-Volatile Memory (NVM)-based neuromorphic hardware. Through detailed circuit-level simulations at scaled process technology nodes, we show the negative impact of technology scaling on the information-processing latency, which impacts the quality-of-service (QoS) of an embedded ML system. At a finer granularity, the latency inside a PE depends on 1) the delay introduced by parasitic components on its current paths, and 2) the varying delay to sense different resistance states of its NVM cells. Based on these two observations, we make the following three contributions. First, on the technology front, we propose an optimization scheme where the NVM resistance state that takes the longest time to sense is set on current paths having the least delay, and vice versa, reducing the average PE latency, which improves the QoS. Second, on the architecture front, we introduce isolation transistors within each PE to partition it into regions that can be individually power-gated, reducing both latency and energy. Finally, on the system-software front, we propose a mechanism to leverage the proposed technological and architectural enhancements when implementing a machine-learning inference task on neuromorphic PEs of the hardware. Evaluations with a recent neuromorphic hardware architecture show that our proposed design-technology co-optimization approach improves both performance and energy efficiency of machine-learning inference tasks without incurring high cost-per-bit.more » « less
-
Deep learning models are increasingly used for end-user applications, supporting both novel features such as facial recognition, and traditional features, e.g. web search. To accommodate high inference throughput, it is common to host a single pre-trained Convolutional Neural Network (CNN) in dedicated cloud-based servers with hardware accelerators such as Graphics Processing Units (GPUs). However, GPUs can be orders of magnitude more expensive than traditional Central Processing Unit (CPU) servers. These resources could also be under-utilized facing dynamic workloads, which may result in inflated serving costs. One potential way to alleviate this problem is by allowing hosted models to share the underlying resources, which we refer to as multi-tenant inference serving. One of the key challenges is maximizing the resource efficiency for multi-tenant serving given hardware with diverse characteristics, models with unique response time Service Level Agreement (SLA), and dynamic inference workloads. In this paper, we present PERSEUS, a measurement framework that provides the basis for understanding the performance and cost trade-offs of multi-tenant model serving. We implemented PERSEUS in Python atop a popular cloud inference server called Nvidia TensorRT Inference Server. Leveraging PERSEUS, we evaluated the inference throughput and cost for serving various models and demonstrated that multi-tenant model serving led to up to 12% cost reduction.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3661825
